Unlock instant, AI-driven research and patent intelligence for your innovation.
A Method of Improving Image Definition Based on Sparse Representation
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for image clarity and sparse representation, applied in the field of image processing, to achieve clear details, enrich detail information, and improve image clarity
Active Publication Date: 2020-08-25
云南联合视觉科技有限公司
View PDF5 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] So far, there is no technology that has the functions of image fusion, high-resolution image reconstruction and image denoising at the same time, so that the final fusion image effect retains the rich details of the source image
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0027] Embodiment 1: A method for improving image clarity based on sparse representation, the specific steps of the method are as follows:
[0028] Step1, the input two pieces of CT and MRI image that pixel size is 256*256 (as image 3 (a), 3(b)), perform low-rank decomposition respectively, and obtain sparse partial images and low-rank partial images respectively; (that is, obtain a low-rank partial image A after CT image decomposition 1 and a sparse partial image A 2 , the MRI image is decomposed to obtain a low-rank partial image B 1 and a sparse partial image B 2 );
[0029] Step2, use the dictionary learning model to select the image set Y (such as Figure 8 As shown, using a high-resolution non-medical image set, this embodiment selects 6 pictures to construct an image set) for training, and obtains a low-rank dictionary D L and a sparse dictionary D S ; The dictionary learning model is:
[0030]
[0031] s.t.||Z S || 0 ≤ T 0 ,||Z L || 0 ≤ T 1
[0032] w...
Embodiment 2
[0036] Embodiment 2: a method for improving image clarity based on sparse representation, the specific steps of the method are as follows:
[0037] Step1, input two noisy CT and MRI images with a pixel size of 256×256 (such as image 3 (c), 3(d)), perform low-rank decomposition respectively, and obtain sparse partial images and low-rank partial images respectively; (that is, after CT image decomposition, a low-rank partial image A 1 and a sparse partial image A 2 , the MRI image is decomposed to obtain a low-rank partial image B 1 and a sparse partial image B 2 );
[0038] Step2, use the dictionary learning model to select the image set Y (such as Figure 8 As shown, using a high-resolution non-medical image set, this embodiment selects 6 pictures to construct) for training, and obtains a low-rank dictionary D L and a sparse dictionary D S ; The dictionary learning model is:
[0039]
[0040] s.t.||Z S || 0 ≤T 0 ,||Z L || 0 ≤T 1
[0041] where Y is denoted as ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
PUM
Login to View More
Abstract
The invention discloses a method for improving image definition based on sparse representation. Two source images are input to perform low-rank decomposition respectively; a dictionary learning model is used to train the selected image set; The sparse part of the image is sparsely fused, and then the low-rank fused image and the sparse fused image are respectively solved by the orthogonal matching pursuit algorithm to obtain the sparse coefficient corresponding to the two parts of the image; the low-rank dictionary is linearly combined with the obtained sparse coefficient to obtain the combination Then use the sparse representation method to perform sparse reconstruction on the combined image to obtain the reconstructed image; then use the orthogonal matching pursuit algorithm to solve the reconstructed image to obtain the sparse coefficient; compare the obtained sparse coefficient with two dictionaries Sparse representation results in fused images. Regardless of whether the present invention looks at the experimental results from the perspective of subjective vision or objective evaluation indicators, the fusion result of the present invention is obviously better than other traditional methods.
Description
technical field [0001] The invention relates to a method for improving image clarity based on sparse representation, which belongs to the field of image processing. Background technique [0002] In the field of image processing, image high-resolution reconstruction technology is a promising research. In recent years, image high-resolution reconstruction technology has attracted more and more researchers' attention. Many researchers have proposed many High-resolution image reconstruction technology method. The so-called high-resolution image reconstruction technology uses a group of low-quality, low-resolution images (or motion sequences) to generate a single high-quality, high-resolution image. The application field of high-resolution image reconstruction is extremely broad, and it has important application prospects in military, medical, public security, computer vision, etc. At present, there are two main categories of high-resolution techniques: reconstruction-based met...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More